© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15667
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Because
    -1.88
     усі
    -1.67
    なんですよ
    -1.61
     leggera
    -1.56
    Because
    -1.50
    Muerte
    -1.49
    umuz
    -1.48
    Usually
    -1.44
     silnik
    -1.43
     Basically
    -1.41
    POSITIVE LOGITS
     a
    2.36
     of
    1.77
     was
    1.63
    aurait
    1.61
     воспользоваться
    1.59
     now
    1.53
    一旁的
    1.52
    を
    1.48
    ⤦
    1.47
     của
    1.45
    Activations Density 0.093%

    No Known Activations